I would not like to crop, but padding is a good idea
My understanding is that the probability would add up to 1 in the end, so one still has some sort of classification going on. But I would like to definitely classify it as neither.
Not a widget for this yet. You could display the top losses, get their filenames and move them manually.
For the widget the images are rescaled (not cropped) to 300, 250.
3 Likes
torch.save(learn.model,"/yourpath/model.pt")
model = torch.load("/yourpath/model.pt")
Hey for
‘download_images(‘data/iphone/iphone.txt’, ‘data/iphone/iphone’, max_pics=200)’
I get ‘NameError: name ‘download_images’ is not defined’
I imported fastai and just updated the library a while back. How to fix this issue?
1 Like
Why does the plot_losses plots val loss after one epoch rather than from first iteration itself?
When I train a learner for one epoch and then repeat that step (e.g. train for another epoch). Is that equivalent to training for 2 epochs right away?
4 Likes
If FileDeleter has the option to feed in a path, and it displayed images within subfolders (classes) in that path with the class labels, it would help in weeding out incorrectly labeled images. This is especially useful when you’re downloading images from Google using the javascript method.
The validation loss is only computed at the end of each epoch, that’s why.
2 Likes
Would it make sense to get ride of all images that have a high loss or is this breaking some rules? Like, Anything that is really wrong, gets thrown out or thrown into a new model where a new model trains on the new images
That is indeed surprising. How come DL is so robust to overfitting when your model has such high capacity?
3 Likes
I can imagine setting up an overfitting situation where the validation set is way different than the training set
oh ok! so training loss is for each iteration whereas val loss is at epoch level in the graph!! shudnt training loss be at epoch level as well to make a fair comparison?
Why is it important for the training loss be smaller than the validation loss? What’s the theory behind that?
2 Likes
Assuming the images are not really messed up, this usually wouldn’t be a good idea. Usually you’re interested in predicting correctly on unknown images, so if you just throw out all the images it gets wrong, it will probably suck at predicting images like that in the future.
1 Like
If you have trained on a bunch of data and all of a sudden see new kinds of data, say orange bears, the trained model would be an over-fit correct? is there a way to overcome such a case? meaning: how generalize can I make my training process?
You are learning the features on the labelled examples. When confronted with novel, previously unseen images, some of the learned features will be useful - but others won’t be. So you don’t expect to do as well on novel images as on the training data.
1 Like
The error being talked about is cross validation error I assume?
1 Like